INDEX

Explanations

Names, locations, and code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¨ĺ

-0.26

embr

-0.26

tre

-0.25

 embr

-0.25

emb

-0.24

ain

-0.24

 Ø§ÙĦØ£Ø³

-0.24

.Strict

-0.23

åŃĶ

-0.23

 tight

-0.23

POSITIVE LOGITS

Ð¾Ð»Ð¾Ð³

0.27

baugh

0.26

Ã¤ge

0.25

åı£å¾Ħ

0.25

schlÃ¤

0.24

<Account

0.24

 Ã©c

0.24

 sands

0.23

åľ°ä¸Ńæµ·

0.23

 historians

0.23

Activations Density 0.046%

Names, locations, and code

No Comments

No Known Activations